Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inherently
    0.46
     ilusión
    0.45
    Biden
    0.44
     преимущества
    0.44
    展现
    0.44
    优势
    0.44
    évaluation
    0.44
    Disponible
    0.43
     வடிவ
    0.43
    更大
    0.43
    POSITIVE LOGITS
     during
    0.70
     During
    0.62
    during
    0.58
     podczas
    0.51
     durant
    0.51
     během
    0.50
     durante
    0.48
     Podczas
    0.48
     tijdens
    0.47
     במהלך
    0.47
    Act Density 0.002%

    No Known Activations